Sonar Pro Search

It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform. Sonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools.

ChatPerplexity200k tokens$3.2702 / $16.3509 · 1M

perplexity/sonar-pro-search

Context
200k tokens
Completion cap
8,000
Tools
No
JSON
Yes
Released
2025-10-30

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perplexity/sonar-pro-search",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Sonar Pro Search?
It is designed for deeper reasoning and analysis. Pricing is based on tokens plus $18 per thousand requests. This model powers the Pro Search mode on the Perplexity platform. Sonar Pro Search adds autonomous, multi-step reasoning to Sonar Pro. So, instead of just one query + synthesis, it plans and executes entire research workflows using tools. Sonar Pro Search runs on the Geek Hub API (OpenAI-compatible). Model id: perplexity/sonar-pro-search.
Is Sonar Pro Search free?
No. Input is $3.2702 per 1M tokens and output is $16.3509 per 1M tokens on Geek Hub (markup included).
What is the context length of Sonar Pro Search?
Sonar Pro Search has a 200k tokens context window. It supports up to 8,000 completion tokens.
Does Sonar Pro Search support tool calling and structured outputs?
Sonar Pro Search does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was Sonar Pro Search released?
Sonar Pro Search was released on 2025-10-30.

More models from Perplexity